Abstract: Provided are methods for image depth estimation, which can include obtaining image associated with a scene of an autonomous vehicle, determining a first estimated depth for a plurality of points in the image, and generating a plurality of groups of points based on the first estimated depth for the plurality of points. Some methods described also include determining a second estimated depth for at least one point using a range specific depth estimation head, determining at least one object classification for the at least one point, and causing the autonomous vehicle to be navigated based on the second estimated depth for the at least one point and the at least one object classification for the at least one point. Systems and computer program products are also provided.

Abstract: Provided are methods and systems for aggregating data associated with various geographic areas for trajectory determination and high definition map generation. The methods and systems may include obtaining first data associated with a first area that is external to a vehicle, converting the first data associated with the first area from a first format to a second format, transmitting the first data that is converted and a query associated with a second area, receiving second data specific to the second area responsive to the query, aggregating the second data specific to the second area with the first data, determining, using the at least one processor, a trajectory of the vehicle within a physical space based on the aggregating of the second data with the first data, and/or generating a graphical representation for use by a display of the vehicle based on the second data that is aggregated with the first data.

Abstract: A system may be used to determined object characteristics and/or generate bounding boxes for objects in a vehicle scene by enriching later-in-time feature maps using earlier-in-time feature maps. The system may generate a feature map from a received. Using an earlier-in-time feature map, the system may enrich semantic data of the generated feature map to form an enriched feature map. The system may use the enriched feature map to generate one or more object characteristics of an object in the scene.

Abstract: A method for real-time semantic image segmentation using a monocular event-based sensor includes capturing a scene using a red, green, blue (RGB) sensor to obtain a plurality of RGB frames and an event sensor to obtain event data corresponding to each of the plurality of RGB frames, performing object labeling for objects in a first RGB frame among the plurality of RGB frames by identifying one or more object classes, obtaining an event velocity of the scene by fusing the event data corresponding to the first RGB frame and at least one subsequent RGB frame among the plurality of RGB frames, determining whether the event velocity is greater than a predefined threshold, and performing object labeling for objects in the at least one subsequent RGB frame based on the determination.

Abstract: A method for real-time semantic image segmentation using a monocular event-based sensor includes capturing a scene using a red, green, blue (RGB) sensor to obtain a plurality of RGB frames and an event sensor to obtain event data corresponding to each of the plurality of RGB frames, performing object labeling for objects in a first RGB frame among the plurality of RGB frames by identifying one or more object classes, obtaining an event velocity of the scene by fusing the event data corresponding to the first RGB frame and at least one subsequent RGB frame among the plurality of RGB frames, determining whether the event velocity is greater than a predefined threshold, and performing object labeling for objects in the at least one subsequent RGB frame based on the determination.